My crit rubric is now an agent instruction

I knew my dark mode looked off. I could not say why. Five written rules could.

AI-built UI drifts to the same place: violet grays, a glow behind everything, a lavender button. Anthropic calls it distributional convergence (opens in a new tab). Left alone, a model picks the safest, most common choice every time.

Studio already had the fix. It is called a crit. The only change is where it lives.

What the rules caught, before and after
My previous theme. Before: violet surfaces and a lavender button. After: warm black, ivory type, cobalt only where it means something.

I use Impeccable (opens in a new tab), an open-source skill that gives coding agents a design vocabulary. It flagged what I had stopped seeing, including 29 cobalt glows, from my previous theme, that read as pigment on paper and as stains on black.

Then I wrote my own rules down. These are the five I now give every agent:

Five crit rules I give every coding agent
Steal these. Change them until they sound like your taste, not mine.

They live in one file the agent reads before it touches a page:

The rules as a Claude Code skill file
A skill is a folder with a SKILL.md: a name, a description, then instructions.

The format is Anthropic’s Agent Skills (opens in a new tab). Drop the folder in .claude/skills and Claude Code picks it up.

Then run the crit before you let it fix anything:

Prompt

Use the crit skill on this page. List every violation with the file, the line and
the rule it breaks. Do not change any code until I choose which ones to fix.

Findings first, fixes second. The agent reports. You still decide.

A crit was always rules in someone’s head. Write them down.

Want it as slides? Download the carousel.